Once your Overdub voice has been trained and activated, open a project to start using it. In order for Descript to know which voice to use, you will need to associate the Overdub voice to a speaker label in your project which you can do in one of two ways:
First you may select the voice in the speaker label dropdown menu. Overdub voices will be listed at the bottom of your speaker label list under the "Create from voice" speaker label section.
Alternately, if a label already exists for the speaker in question (for example if you've already imported and transcribed a recording), you may associate the Overdub voice to an existing speaker label by clicking on the label, selecting Edit speakers, then selecting the Overdub voice from the dropdown button on the right.
Creating an Overdub is as easy as typing on a blank line just as you would in any text editor. You can do this either in a new Composition, or by creating a new line in the middle of an existing recording.
After waiting a few seconds, you will see the message "Generating Overdub" while the speech audio is created. Once complete, the blue underline will disappear and a new waveform will appear in the timeline below.
You can also insert or replace audio in the middle of a pre-existing recording by clicking the location you would like it to appear in, or highlighting a section of text and pressing the letter D in the pop up dialog. When finished, click the Overdub button or press Enter.
Working with Sequences
Please note that Overdub can be used on standard audio and video files in the timeline editor, however when applying Overdub to multitrack Sequences, the Sequence clip will be replaced with an Overdub clip. If the Sequence contains video, it is expected that the video for that clip will be blank. We do expect to support this more fully in the future.
Overdub Styles (experimental)
You can also create different intonation patterns or emotional palettes of your Overdub voice by creating a Style. Just select 5-10 seconds of real recorded audio that more or less mimics the intonation pattern you're looking for, right-click the selection, then click Overdub > Create new Voice style. Add a name that describes your new style then click Create when finished.
Once created, you can switch to your new style by clicking on the Speaker Label, hovering over your Overdub voice and selecting it from the list of available Styles.
Style Source Material
Styles can only be created from highlighted sections of real recorded audio. If Descript detects a clip in your selection that was generated with Overdub, the Style will not be created.
Voices created on the Free or Creator plans will get a demo version of Overdub with a 1,000-word vocabulary - any words that are not that list will be replaced with "jibber" and "jabber" (and a few others) while demoing the feature. Upgrading to the Pro plan will unlock the full version of Overdub with unlimited vocabulary. See our Managing your Drive Plan article for details on how to upgrade.
Frequently Asked Questions
How can I improve the quality of my Overdub voice?
Overdub voice quality relies on a number of factors such as the quality of your microphone, background noise, and room surfaces. Check out our article Overdub Voice Quality Tips for tips on how you can assure the best possible recording.
I want to create a Style from a section of audio, but it's too long because it also selects the silence afterward. How can I prevent that?
To prevent Descript from selecting the full silence after a section of text you can right-click in the timeline just after your phrase and select Split Clip.